HyperAI
HyperAI超神経
ホーム
プラットフォーム
ドキュメント
ニュース
論文
チュートリアル
データセット
百科事典
SOTA
LLMモデル
GPU ランキング
学会
検索
サイトについて
利用規約
プライバシーポリシー
日本語
HyperAI
HyperAI超神経
Toggle Sidebar
サイトを検索…
⌘
K
Command Palette
Search for a command to run...
プラットフォーム
ホーム
SOTA
マルチスペクトル物体検出
Multispectral Object Detection On Kaist
Multispectral Object Detection On Kaist
評価指標
All Miss Rate
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
Columns
モデル名
All Miss Rate
Paper Title
FusionRPN+BF
51.70
Fully Convolutional Networks for Semantic Segmentation
Halfway Fusion
49.18
Multispectral Deep Neural Networks for Pedestrian Detection
IATDNN+IASS
48.96
Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection
IAFR-CNN
44.23
Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
CIAN
35.53
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
AR-CNN
34.95
Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
MSDS-R-CNN
34.15
Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
MBNet
31.87
Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
TSFADet
30.74
Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection
CMPD
28.98
Confidence-aware Fusion using Dempster-Shafer Theory for Multispectral Pedestrian Detection
C2former
28.39
$\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
UniRGB-IR
25.21
UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning
RSDet
24.79
Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection
MLPD
-
MLPD: Multi-Label Pedestrian Detector in Multispectral Domain
CFR
-
Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks
INSANet
-
INSANet: INtra-INter Spectral Attention Network for Effective Feature Fusion of Multispectral Pedestrian Detection
GAFF
-
Guided Attentive Feature Fusion for Multispectral Pedestrian Detection
0 of 17 row(s) selected.
Previous
Next